Yuanxiang Heng
hyxmmm
AI & ML interests
None yet
Organizations
hyxmmm's activity
About `system_prompt` setting when fine-tuning by this dataset
2
#22 opened 16 days ago
by
Remixa
What is the Differences and Overlap between 7M, 7M Domain, Gen and 0625?
2
#23 opened 15 days ago
by
alpayariyak
git lfs pull 失败
1
#21 opened 17 days ago
by
zheong
Does two stage training use same hyperparamers?
2
#3 opened 25 days ago
by
bbruceyuan
关于3M数据和chat数据的使用
6
#10 opened 2 months ago
by
Spurslipu
Will Consider Continue SFT?
1
#1 opened 2 months ago
by
kevinpro
指令数据集的类别映射问题
1
#19 opened 24 days ago
by
Alwin114
3M 和 7M 的中文数据是相同的吗?
1
#18 opened 30 days ago
by
xianf
ft base model
1
#2 opened about 1 month ago
by
xxllp
the perspective of instruction compliance
1
#17 opened about 1 month ago
by
YvanLee
关于8月新更新的数据集问题
5
#14 opened about 2 months ago
by
Spurslipu
0729聊天数据集有计划开源吗?
2
#16 opened about 1 month ago
by
yixinsong
0625 Split Error: `pyarrow.lib.ArrowInvalid: Expected to read 538970747 metadata bytes, but only read 1072`
2
#15 opened about 1 month ago
by
Avelina
What is the context length in training?
1
#1 opened 2 months ago
by
xuxiu
数据有问题,处理的格式不一致,导致最新的版本用不了
2
#12 opened 2 months ago
by
Amu
部分对话开头应该是来自系统
1
#11 opened 2 months ago
by
VIPSP
这个会出4bits量化版本吗?
2
#1 opened 11 months ago
by
hanswang73
这个模型真的有16K上下文长度吗?
1
#2 opened 11 months ago
by
jiyintor